updated numba_dpex kernel call to use new API (#2394)

Author: Ankur-singh

AI-and-Analytics/Features-and-Functionality/IntelPython_Numpy_Numba_dpex_kNN/IntelPython_Numpy_Numba_dpex_kNN.ipynb

@@ -331,6 +331,7 @@
     "\n",
     "@numba_dpex.kernel\n",
     "def knn_numba_dpex(\n",
+    "    item: numba_dpex.kernel_api.Item,\n",
     "    train,\n",
     "    train_labels,\n",
     "    test,\n",
@@ -339,8 +340,8 @@
     "    votes_to_classes_lst,\n",
     "):\n",
     "    dtype = train.dtype\n",
-    "    i = numba_dpex.get_global_id(0)\n",
-    "    queue_neighbors = numba_dpex.private.array(shape=(3, 2), dtype=dtype)\n",
+    "    i = item.get_id(0)\n",
+    "    queue_neighbors = numba_dpex.kernel_api.PrivateArray(shape=(3, 2), dtype=dtype)\n",
     "\n",
     "    for j in range(k):\n",
     "        x1 = train[j, 0]\n",
@@ -436,8 +437,15 @@
     "y_train_dpt = dpnp.asarray(y_train.values, device=\"cpu\")\n",
     "X_test_dpt = dpnp.asarray(X_test.values, device=\"cpu\")\n",
     "\n",
-    "knn_numba_dpex[numba_dpex.Range(len(X_test.values))](\n",
-    "    X_train_dpt, y_train_dpt, X_test_dpt, 3, predictions, votes_to_classes_lst\n",
+    "numba_dpex.call_kernel(\n",
+    "    knn_numba_dpex,\n",
+    "    numba_dpex.Range(len(X_test.values)),\n",
+    "    X_train_dpt,\n",
+    "    y_train_dpt,\n",
+    "    X_test_dpt,\n",
+    "    3,\n",
+    "    predictions,\n",
+    "    votes_to_classes_lst,\n",
     ")"
    ]
   },

AI-and-Analytics/Features-and-Functionality/IntelPython_Numpy_Numba_dpex_kNN/IntelPython_Numpy_Numba_dpex_kNN.py

@@ -157,6 +157,7 @@ def knn(X_train, y_train, X_test, k):
 
 import numba
 
+
 @numba.jit(nopython=True)
 def euclidean_distance_numba(vector1, vector2):
     dist = np.linalg.norm(vector1 - vector2)
@@ -173,7 +174,6 @@ def knn_numba(X_train, y_train, X_test, k):
     # 1. Prepare container for predictions
     predictions = np.zeros(X_test.shape[0])
     for x in np.arange(X_test.shape[0]):
-
         # 2. Calculate distances
         inputs = X_train.copy()
         distances = np.zeros((inputs.shape[0], 1))
@@ -235,8 +235,10 @@ def knn_numba(X_train, y_train, X_test, k):
 
 import numba_dpex
 
+
 @numba_dpex.kernel
 def knn_numba_dpex(
+    item: numba_dpex.kernel_api.Item,
     train,
     train_labels,
     test,
@@ -245,8 +247,8 @@ def knn_numba_dpex(
     votes_to_classes_lst,
 ):
     dtype = train.dtype
-    i = numba_dpex.get_global_id(0)
-    queue_neighbors = numba_dpex.private.array(shape=(3, 2), dtype=dtype)
+    i = item.get_id(0)
+    queue_neighbors = numba_dpex.kernel_api.PrivateArray(shape=(3, 2), dtype=dtype)
 
     for j in range(k):
         x1 = train[j, 0]
@@ -333,8 +335,15 @@ def knn_numba_dpex(
 y_train_dpt = dpnp.asarray(y_train.values, device="cpu")
 X_test_dpt = dpnp.asarray(X_test.values, device="cpu")
 
-knn_numba_dpex[numba_dpex.Range(len(X_test.values))](
-    X_train_dpt, y_train_dpt, X_test_dpt, 3, predictions, votes_to_classes_lst
+numba_dpex.call_kernel(
+    knn_numba_dpex,
+    numba_dpex.Range(len(X_test.values)),
+    X_train_dpt,
+    y_train_dpt,
+    X_test_dpt,
+    3,
+    predictions,
+    votes_to_classes_lst,
 )
 
 
@@ -352,4 +361,4 @@ def knn_numba_dpex(
 # In[ ]:
 
 
-print("[CODE_SAMPLE_COMPLETED_SUCCESSFULLY]")
+print("[CODE_SAMPLE_COMPLETED_SUCCESSFULLY]")